Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1231 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1536161 (Python Code)

Max Activating Token Index: 681

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1133307 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1286738 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1063775 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0266. Min Act: -0.0001

Data Index: 25367 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0251. Min Act: -0.0001

Data Index: 620036 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1349650 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1368923 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1565497 (Python Code)

Max Activating Token Index: 538

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0264. Min Act: -0.0001

Data Index: 916574 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0249. Min Act: -0.0000

Data Index: 196446 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0247. Min Act: -0.0000

Data Index: 931735 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0251. Min Act: -0.0000

Data Index: 38800 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0231. Min Act: -0.0000

Data Index: 568986 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0234. Min Act: -0.0000

Data Index: 1410751 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0249. Min Act: -0.0001

Data Index: 848200 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1352335 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0251. Min Act: -0.0000

Data Index: 210129 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0224. Min Act: -0.0001

Data Index: 880566 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1067447 (C4 (Web Text))

Max Activating Token Index: 410